Overview
What this challenge is about.
You implement four chunking strategies on financial filings, test retrieval and answer accuracy, then recommend one strategy. You get a verifiable certificate.
The scenario
The startup (Series A, around 50 staff, ARR around USD 7M) loses about 20 percent of trials on numerical-question quality; the product VP has prioritized chunking as the most likely root cause.
The Brief
What you'll do, and what you'll demonstrate.
Compare 4 chunking strategies on a 10-K research assistant and recommend one that lifts numerical-question accuracy without regressing on narrative.
Earning criteria — what you'll demonstrate
- Implement and compare 4 chunking strategies on real documents
- Design a fair evaluation that separates narrative and numerical questions
- Reason about chunking trade-offs (granularity, table preservation, embedding quality)
- Document the recommendation for a non-research engineering team
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Retrieval-Augmented Generation
Master · Ai Systems
Strong alignment
This challenge maps to Retrieval-Augmented Generation at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Document Chunking
Apply document chunking to solve real industry problems and demonstrate production-level capability.
- Semantic Chunking
Apply semantic chunking to solve real industry problems and demonstrate production-level capability.
- Layout Aware Chunking
Apply layout aware chunking to solve real industry problems and demonstrate production-level capability.
- Rag Evaluation
Apply rag evaluation to solve real industry problems and demonstrate production-level capability.
- Python
Write clean, efficient Python for data processing, automation, and backend services.
- Experiment Design
Apply experiment design to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
AI Engineer
Running structured chunking bake-offs on real documents is the kind of evaluation work AI engineers do constantly when shipping RAG products.
This challenge sharpens
- document-chunking
- rag-evaluation
- experiment-design
NLP Engineer
Layout-aware and semantic chunking choices are core NLP-engineer territory in document-AI teams.
This challenge sharpens
- semantic-chunking
- layout-aware-chunking
- document-chunking
Applied AI Scientist
Comparing 4 strategies on the right question-type split and writing a methodology note is applied-AI-scientist judgement work.
This challenge sharpens
- experiment-design
- rag-evaluation
- document-chunking